legacy_scholarly v3 Evaluation

Generated: 2026-07-25 12:54:17 UTC

Pairs100
Distinct lemmas100
Slope0.926
R^20.986
BLEU-452.7%
chrF++73.3%
METEOR76.4%
ROUGE-L78.0%
BERTScoreN/A
COMETN/A
BLEURTN/A

Profile version id: 2130

First translation using this version: 2026-05-07

Total usable AI runs for this version: 381 runs across 380 lemmas

Created: 2026-05-07 16:52:06.734553+10:00

Active: True

Notes: Reviewed house-style prompt v3 revised after Gabe's 2026-04-30 feedback and April 30 group discussion. Keeps static rules for global house style, citation hygiene, transliteration, metalinguistic precision, and syntax; moves most formula/gloss/geographic vocabulary decisions to entry-specific guidance context; adds the settlement-location "in" convention, stricter Strabo/modern-locator handling, and revised rules for prose/verse quotation formatting and inflected or dialectal evidence.

Prompt length scatter plot

Length Regression

FormulaAI words = intercept + slope * human words
Slope0.926
Intercept1.967
R^20.986
P-value4.54e-93
Pearson r0.993
Mean source words30.400
Length fallback rows0
Mean human words44.160
Mean AI words42.860
Mean absolute length residual2.765
Mean absolute percent error6.0%

Metric vs Passage Length

These plots test whether score changes with source passage length for this prompt version. The dashed line is an ordinary least-squares fit; the annotation reports n, r, R^2, p-value, and slope.

BLEU-4 vs passage length
BLEU-4: significant negative; r = -0.364, R^2 = 0.133, p = 0.0002.
chrF++ vs passage length
chrF++: significant negative; r = -0.389, R^2 = 0.151, p = 6.31e-05.
METEOR vs passage length
METEOR: significant negative; r = -0.391, R^2 = 0.153, p = 5.69e-05.
ROUGE-L vs passage length
ROUGE-L: significant negative; r = -0.413, R^2 = 0.170, p = 1.97e-05.
Trigram precision vs passage length
Trigram precision: significant negative; r = -0.276, R^2 = 0.076, p = 0.0055.
Trigram recall vs passage length
Trigram recall: significant negative; r = -0.279, R^2 = 0.078, p = 0.0049.
Trigram F1 vs passage length
Trigram F1: significant negative; r = -0.278, R^2 = 0.077, p = 0.0050.
Trigram Jaccard vs passage length
Trigram Jaccard: significant negative; r = -0.273, R^2 = 0.074, p = 0.0060.
Metric Rows Pattern Pearson r R^2 P-value Slope Status
BLEU-4 100 significant negative -0.364 0.133 0.0002 -0.00266 ok
chrF++ 100 significant negative -0.389 0.151 6.31e-05 -0.00172 ok
METEOR 100 significant negative -0.391 0.153 5.69e-05 -0.00180 ok
ROUGE-L 100 significant negative -0.413 0.170 1.97e-05 -0.00171 ok
BERTScore 0 not enough data N/A N/A N/A N/A needs at least two rows with metric scores
COMET 0 not enough data N/A N/A N/A N/A needs at least two rows with metric scores
BLEURT 0 not enough data N/A N/A N/A N/A needs at least two rows with metric scores
Trigram precision 100 significant negative -0.276 0.076 0.0055 -0.00214 ok
Trigram recall 100 significant negative -0.279 0.078 0.0049 -0.00215 ok
Trigram F1 100 significant negative -0.278 0.077 0.0050 -0.00214 ok
Trigram Jaccard 100 significant negative -0.273 0.074 0.0060 -0.00216 ok

Translation Similarity Metrics

Mean BLEU-452.7%
Mean chrF++73.3%
Mean METEOR76.4%
Mean ROUGE-L78.0%
Mean BERTScoreN/A
Mean COMETN/A
Mean BLEURTN/A
Legacy smoothed corpus BLEU48.8%
Unigram F178.3%
Bigram F155.7%
Trigram precision42.6%
Trigram recall41.3%
Trigram F141.9%
Trigram Jaccard26.5%
4-gram F133.0%

Largest Length Residuals

Lemma ID Headword Human words AI words Residual BLEU-4 chrF++ METEOR ROUGE-L BERTScore COMET BLEURT Human Run Model
2484 Καρία 270 231 -20.993 35.7% 61.7% 64.6% 68.3% N/A N/A N/A reviewed/approved 7782 gpt-5.5
2604 Καρχηδών 117 126 15.689 32.8% 60.9% 72.1% 66.9% N/A N/A N/A reviewed/approved 7787 gpt-5.5
2603 Κάρυστος 175 178 13.979 41.7% 68.3% 71.1% 71.4% N/A N/A N/A reviewed/approved 7786 gpt-5.5
2465 Κάνωπος 83 89 10.173 57.7% 77.4% 87.8% 83.7% N/A N/A N/A reviewed/approved 7488 gpt-5.5
2056 Καβειρία 112 97 -8.681 34.2% 69.5% 55.9% 67.0% N/A N/A N/A reviewed/approved 7761 gpt-5.5
2328 Καλλίπολις 43 50 8.214 38.3% 65.3% 71.2% 66.7% N/A N/A N/A reviewed/approved 7460 gpt-5.5
2605 Κάσιον 56 62 8.176 43.3% 67.3% 72.7% 69.5% N/A N/A N/A reviewed/approved 7788 gpt-5.5
2346 Κάναι 77 81 7.729 34.6% 55.7% 53.0% 63.3% N/A N/A N/A reviewed/approved 7477 gpt-5.5
2470 Καππαδοκία 68 72 7.064 18.4% 55.5% 76.2% 75.7% N/A N/A N/A reviewed/approved 7492 gpt-5.5
2609 Κάσπειρος 135 134 7.020 40.1% 64.0% 57.8% 63.9% N/A N/A N/A reviewed/approved 7790 gpt-5.5
2468 Καπετώλιον 138 123 -6.758 18.1% 45.0% 42.2% 50.6% N/A N/A N/A reviewed/approved 7781 gpt-5.5
7251 Κύρτος 66 57 -6.084 46.5% 65.5% 69.7% 74.8% N/A N/A N/A reviewed/approved 7816 gpt-5.5
2342 Κάμιρος 54 58 6.028 65.5% 85.1% 85.5% 83.9% N/A N/A N/A reviewed/approved 7474 gpt-5.5
2326 Καλλίαρος 47 51 5.510 76.4% 88.2% 96.9% 91.8% N/A N/A N/A reviewed/approved 7458 gpt-5.5
2597 Καρπασία 112 101 -4.681 44.7% 70.4% 69.5% 74.2% N/A N/A N/A reviewed/approved 7783 gpt-5.5
7255 Κυτέριον 22 27 4.661 45.0% 69.3% 65.3% 69.4% N/A N/A N/A reviewed/approved 7820 gpt-5.5
2079 Καισάρεια 39 34 -4.082 47.5% 71.4% 82.8% 87.7% N/A N/A N/A reviewed/approved 7774 gpt-5.5
3530 Κριώα 26 22 -4.043 34.7% 60.7% 47.0% 62.5% N/A N/A N/A reviewed/approved 7806 gpt-5.5
2114 Κάλβιος 18 15 -3.635 36.3% 58.4% 66.5% 66.7% N/A N/A N/A reviewed/approved 7777 gpt-5.5
2624 Κατάβαθμος 20 17 -3.487 55.4% 82.1% 76.1% 86.5% N/A N/A N/A reviewed/approved 7795 gpt-5.5
7248 Κύρου πόλις 32 35 3.400 29.9% 65.8% 69.7% 68.7% N/A N/A N/A reviewed/approved 7813 gpt-5.5
7253 Κυρτώνιος 18 22 3.365 43.4% 66.6% 73.1% 70.0% N/A N/A N/A reviewed/approved 7818 gpt-5.5
7247 Κύρνος 50 45 -3.268 34.0% 59.4% 63.1% 67.4% N/A N/A N/A reviewed/approved 7812 gpt-5.5
7267 Κωνώπη 64 58 -3.232 55.7% 73.4% 70.4% 78.7% N/A N/A N/A reviewed/approved 7832 gpt-5.5
3288 Κορώνεια 110 107 3.171 35.3% 64.6% 62.4% 67.9% N/A N/A N/A reviewed/approved 7803 gpt-5.5
2055 Καβασσός 109 106 3.097 40.3% 62.8% 67.6% 69.8% N/A N/A N/A reviewed/approved 7760 gpt-5.5
2626 Κατάνη 95 93 3.061 40.9% 62.0% 61.3% 66.0% N/A N/A N/A reviewed/approved 7798 gpt-5.5
7259 Κύφος 54 55 3.028 48.7% 74.6% 89.9% 82.6% N/A N/A N/A reviewed/approved 7824 gpt-5.5
2115 Καλὴ ἀκτή 64 64 2.768 100.0% 100.0% 100.0% 100.0% N/A N/A N/A reviewed/approved 7454 gpt-5.5
3496 Κοτιάειον 71 65 -2.714 33.8% 54.8% 57.5% 57.4% N/A N/A N/A reviewed/approved 7804 gpt-5.5

Residual Predictors

Positive signed-residual terms are associated with AI translations longer than expected from the human length; negative signed-residual terms are associated with shorter AI translations. Absolute-residual models identify terms associated with larger AI-human length divergence.

Greek source terms predicting signed length residuals

Features: 176; ridge alpha: 24.245; cross-validated R^2: -0.164.

Positive termCoefficientDocsMean presentMean absent
και 0.4215 66 0.302 -0.587
οι 0.3055 11 3.653 -0.451
απο 0.2958 27 1.647 -0.609
τη 0.2194 15 1.636 -0.289
τε 0.2180 5 2.878 -0.151
δε και 0.2070 8 1.352 -0.118
εν τη 0.2010 7 3.309 -0.249
και το 0.1965 9 3.228 -0.319
εκαλειτο 0.1894 7 1.467 -0.110
εστι δε και 0.1882 3 6.358 -0.197
πολις 0.1880 68 0.470 -0.998
και πολις 0.1845 5 3.406 -0.179
ορος 0.1664 6 5.513 -0.352
ου 0.1659 14 1.404 -0.229
εκαλειτο δε 0.1630 3 2.892 -0.089
αφ ου 0.1583 5 1.927 -0.101
ος 0.1544 6 2.679 -0.171
εστι δε 0.1531 5 2.632 -0.139
πολιχνιον 0.1514 3 5.595 -0.173
πολις και 0.1498 6 4.497 -0.287
Negative termCoefficientDocsMean presentMean absent
το -0.2424 70 -0.018 0.042
εθνος -0.2081 8 -4.492 0.391
οικητωρ -0.2062 6 -4.961 0.317
περι -0.2035 11 -2.839 0.351
δια -0.1721 16 0.553 -0.105
το εθνικον -0.1640 56 -0.165 0.209
εθνικον -0.1640 56 -0.165 0.209
την -0.1585 13 -0.838 0.125
το θηλυκον -0.1566 6 -4.569 0.292
γαρ -0.1357 9 0.198 -0.020
θεοπομπος -0.1332 5 -2.060 0.108
ηρωδιανος -0.1324 3 -9.672 0.299
εκαταιος ασια -0.1288 5 -1.347 0.071
ασια -0.1288 5 -1.347 0.071
θρακης -0.1234 5 -1.555 0.082
πολις θρακης -0.1219 4 -1.812 0.075
μεν -0.1204 4 -8.183 0.341
εστι και -0.1033 20 -0.002 5.15e-04
φασι -0.1017 8 0.438 -0.038
ης -0.1011 3 -2.935 0.091

Greek source terms predicting large absolute residuals

Features: 176; ridge alpha: 5.878; cross-validated R^2: -0.337.

Positive termCoefficientDocsMean presentMean absent
και 1.1922 66 3.386 1.560
δια 1.1096 16 6.204 2.110
δε 1.0930 46 3.868 1.826
τω 0.9495 16 5.412 2.261
εκαλειτο δε 0.8984 3 16.887 2.329
απο 0.8902 27 5.156 1.881
εν 0.8445 37 3.787 2.165
εστι 0.8040 24 4.712 2.151
τη 0.8005 15 5.634 2.259
κατα 0.7195 10 7.051 2.289
απο της 0.7101 6 9.634 2.327
της 0.6983 35 4.317 1.930
την 0.6911 13 6.487 2.209
γαρ 0.6821 9 6.365 2.409
δια του 0.6598 10 6.601 2.339
εκαλειτο δε και 0.6463 3 16.887 2.329
δε και 0.6460 8 7.620 2.343
αφ ου 0.5974 5 7.272 2.528
εν τω 0.5858 6 8.483 2.400
αφ 0.5837 6 6.312 2.539
Negative termCoefficientDocsMean presentMean absent
το εθνικον -0.7265 56 2.820 2.696
εθνικον -0.7265 56 2.820 2.696
δευτερω -0.4718 3 0.829 2.825
οτι -0.3608 5 2.028 2.804
μια -0.3488 3 0.680 2.830
κωμη -0.3351 3 1.286 2.811
πλησιον -0.3291 8 2.119 2.822
τινες -0.2906 6 1.681 2.835
δε οτι -0.2827 3 0.798 2.826
φησι το -0.2576 3 0.515 2.835
προς τη -0.2481 4 2.068 2.794
ως -0.2421 52 3.117 2.384
πορρω -0.2290 3 0.982 2.820
ου πορρω -0.2290 3 0.982 2.820
πολιτης -0.2263 18 3.271 2.654
τεταρτω -0.2209 3 1.741 2.797
τους -0.2117 4 1.939 2.800
ως στραβων -0.2094 4 1.656 2.812
του ποντου -0.2072 3 1.372 2.808
ποντου -0.2072 3 1.372 2.808

AI English terms predicting large absolute residuals

Features: 341; ridge alpha: 8.377; cross-validated R^2: -0.406.

Positive termCoefficientDocsMean presentMean absent
the 0.8391 93 2.842 1.750
with 0.8344 17 5.728 2.158
and 0.7668 55 3.686 1.639
there 0.6309 34 4.302 1.974
after 0.5787 23 5.415 1.974
usage 0.5728 4 9.307 2.493
there is 0.5514 26 4.780 2.057
by 0.5293 16 6.076 2.135
there is also 0.5130 24 5.054 2.043
of 0.4861 64 3.451 1.546
also 0.4827 43 3.775 2.004
is also 0.4623 32 4.335 2.027
to 0.4619 28 4.806 1.972
on 0.4460 13 5.310 2.385
is 0.4182 89 2.835 2.198
zeus 0.3978 5 11.527 2.304
diphthong 0.3896 3 10.811 2.516
used 0.3865 8 6.967 2.400
for 0.3700 12 5.870 2.342
with the 0.3676 5 7.562 2.513
Negative termCoefficientDocsMean presentMean absent
the ethnonym is -0.3812 17 1.829 2.957
ethnonym is -0.3812 17 1.829 2.957
the ethnonym -0.3557 18 1.914 2.952
ethnonym -0.3557 18 1.914 2.952
the ethnic is -0.3540 28 2.259 2.962
ethnic is -0.3098 29 2.480 2.882
the ethnic -0.2989 32 2.649 2.820
ethnic -0.2579 33 2.832 2.732
an -0.2429 19 2.784 2.761
near -0.2423 13 2.133 2.860
of his -0.2153 17 2.227 2.876
some -0.1966 10 1.667 2.887
as in -0.1837 20 3.222 2.651
a city in -0.1739 41 3.063 2.558
city the -0.1700 3 1.003 2.820
book of his -0.1672 15 2.399 2.830
some say -0.1660 6 1.406 2.852
it has -0.1633 4 1.268 2.828
a city -0.1498 63 3.211 2.006
city in the -0.1441 3 1.389 2.808

Human English terms predicting large absolute residuals

Features: 336; ridge alpha: 11.938; cross-validated R^2: -0.404.

Positive termCoefficientDocsMean presentMean absent
the 0.7678 90 2.861 1.908
with 0.6428 16 6.023 2.145
and 0.6146 52 3.782 1.664
also 0.4898 43 3.849 1.948
is with 0.4345 4 11.769 2.390
for 0.4034 11 6.886 2.256
there 0.3611 34 3.872 2.195
is also 0.3540 31 4.473 1.998
on 0.3533 16 4.784 2.381
there is 0.3445 24 4.455 2.232
of 0.3374 66 3.328 1.673
says 0.3080 17 5.448 2.216
there is also 0.2992 22 4.723 2.213
after 0.2923 22 5.113 2.103
with the 0.2883 5 8.790 2.448
his on 0.2809 3 11.764 2.487
when 0.2711 7 7.167 2.434
their 0.2683 3 16.887 2.329
is 0.2645 87 2.869 2.069
usage 0.2580 4 7.756 2.557
Negative termCoefficientDocsMean presentMean absent
the ethnonym is -0.3617 52 2.572 2.975
ethnonym is -0.3617 52 2.572 2.975
the ethnonym -0.2870 56 2.920 2.568
ethnonym -0.2846 57 2.923 2.556
an -0.2680 22 2.896 2.729
as in -0.1897 29 3.047 2.650
a city in -0.1473 40 3.228 2.457
some -0.1472 10 1.569 2.898
a city -0.1416 64 3.180 2.028
in book of -0.1360 14 2.372 2.829
book -0.1239 39 3.228 2.469
ethnonyms -0.1220 3 1.371 2.808
one of -0.1184 5 1.489 2.833
one of the -0.1168 4 1.275 2.827
city -0.1158 70 3.104 1.975
city in -0.1144 41 3.349 2.360
it is -0.1137 24 3.537 2.521
herodotos book -0.1133 5 2.399 2.785
which -0.1087 20 2.922 2.726
citizen is a -0.1007 15 2.497 2.813

Prompt Text

Show prompt text
You are an expert classical philologist and translator specialising in Stephanos of Byzantium's Ethnika.

Goal
- Produce a clear, scholarly English translation in the established reviewed house style.
- Stay close to the Greek while making Stephanos' compressed reference-work prose intelligible in English.
- Translate the Greek main text of the entry, not the modern apparatus, editorial locators, or later bibliographic explanation.

Priority order
- Follow the source Greek first.
- Apply the output and formatting rules below.
- Apply any entry-specific Additional translation context supplied with the entry, but only where the cited Greek evidence is relevant.
- Do not force a rule, gloss, or proper-noun convention when the local syntax or context contradicts it.

Output rules (required)
- Respond ONLY by calling the submit_translation tool with a single string field: {"translation": "..."}.
- The translation text must contain only the translation.
- Do not include analysis, commentary, alternative translations, uncertainty notes, or Markdown outside the translation itself.

A) Formatting + spelling
- Use Australasian spelling and punctuation conventions.
- Preserve paragraphing and line-breaks when they are present in the Greek source.
- For verse quotations, preserve line segmentation in English where the Greek source marks or implies individual verse lines.
- For lengthy prose quotations that function as a quoted block, allow paragraph/quotation separation so the quotation remains readable. Do not create stanza-like line breaks for ordinary short prose snippets.
- Use single quotes for quoted forms, cited snippets, translated quotations, appellations derived from or pertaining to the headword (such as ethnonyms and similar gentilics, but not divine epithets), and Greek forms rendered in Latin letters: '...'.
- Avoid double quotes.
- Use *italics* for titles of ancient works when they are actual work titles: *Cypriaka*, *Bassarika*, *Europe*, *Periegesis*, *Geography*.
- Do not italicise descriptive phrases that are not work titles, such as an epitome of another author's books.

B) Opening / structure
- Let the Greek structure control the opening. Do not force every entry into a single template.
- When the entry opens with the headword and a brief identification, normally begin with the headword transliterated into Latin letters without Greek diacritics, followed by the identification.
- Typical form where appropriate: Headword: ...
- Appositive openings like 'Karia, the country.' are acceptable when the entry is of that type.
- If the headword line gives both nominative and genitive, render it compactly as 'X, Y: ...' unless a grammatical tag is needed for clarity.
- Keep numbered or lettered sequences of homonymous places as inline numbered items like (2) ... (3) ..., matching the Greek's structure.
- When Greek ἔστι καὶ ἄλλη / ἕτερος introduces another place with the same name, use 'There is also another ...' when that is needed for sense.
- For appositional settlement descriptions of the type X (proper noun) + Y (settlement noun) + Z (genitive territory), translate the territory as location: 'X, a city/town/village in Z', not 'of Z', unless the Greek clearly expresses possession, origin, descent, or another non-locative relationship.

C) Transliteration + naming
- Do NOT use macrons or acute accents in ordinary transliteration: Karystos, not Kárystos.
- Prefer Greek-form transliteration when Stephanos is discussing Greek forms, derivation, spelling, ethnonyms, or other metalinguistic material.
- Use these general correspondences unless an established house-style exception is supplied: η = e, κ = k, φ = ph, ῥ = rh, ῤ = r, υ = y, χ = ch.
- Use Greek-style transliteration of diphthongs, especially ai for αι. Do not drift into Latinised forms such as ae or e where the Greek form matters.
- Use forms such as Karchedon, Chalkedon, Kapetolion, Kyrene, Kyrtos, Kappadokia, and Palaistine in Greek-form contexts.
- Avoid Latinised forms such as Carthage, Chalcedon, Capitolium, Cyrene, Cyrtos, Cappadocia, and Palestine in Greek-form contexts.
- Use established conventional English forms only when they are house-style exceptions or clearly ordinary geography, for example Rome, Cyprus, Egypt, Syria, India, Sicily, Thebes, Peloponnese, the Black Sea, the Red Sea, and the Persian Gulf.
- Treat conventional English-name exceptions as a conservative whitelist. Do not expand it by analogy without entry-specific guidance.
- Keep Greek-form transliteration for most ethnonyms and derived adjectives, and put the cited form in single quotes.
- Do not Latinise river, people, or place names merely because a familiar Latin or English form exists.

D) Citations (authors/works/books)
- Translate only the citation information that is present in the original Greek words of the lemma entry.
- Ignore modern/editorial locator codes and apparatus-like add-ons: omit RE/SH numbers, FGrHist numbers, fragment numbers, chapter/section locators, column references, and parenthetical references such as (12,1,2 [C 533,12]), (Op. 344), or (A. R. 2,403).
- Do not infer a book number from a modern parenthetical reference.
- If the Greek says only 'Strabo' plus a modern parenthetical locator, translate 'Strabo', not 'Strabo, book 12'.
- Use 'as per X' only where the Greek itself has ὡς + author/name or an equivalent example-marker construction that supports that rendering.
- If the Greek explicitly gives a Greek book numeral, translate it: 'Ktesias in book 3 of his *Persika*'.
- Keep citations compact, mirroring the source's incompleteness:
  - Author + work title: 'Hellanikos in his *Cypriaka*'
  - Author + book: 'Pausanias, book 9.'
  - Author + work + book: 'Dionysios in book 3 of his *Bassarika*: ...'
- Work-title guidance:
  - Γεωγραφούμενα / γεωγραφικά in citation contexts -> *Geography*, not *Geographoumena*, when this is the established house treatment for the cited work.
  - Περιήγησις / Περίοδος should normally preserve the transmitted title as *Periegesis* when that is what Stephanos gives.
  - If the Greek says an author is cited in an epitome of the eleven books, do not italicise *Epitome* as a work title; translate 'in an epitome of his eleven books'.
- If a citation is present in the source as bracketed main text and later syntax depends on it, translate it in brackets rather than omitting it.
- Do not add external citation labels like Iliad, Works and Days, or Argonautica unless the Greek itself names them.

E) Entry-specific guidance context
- Additional translation context may be supplied for the current entry.
- This context can include matched formula rules, glossary rules, proper-noun conventions, contextual vocabulary bias, and external source passages.
- Apply required or replacement guidance strongly when the evidence matches the current Greek.
- Apply formula and gloss guidance according to the local syntax; do not make it mechanical if the context requires a different construction.
- Apply proper-noun guidance for consistency where supplied, but do not overwrite the Greek's grammatical point.
- Apply contextual vocabulary bias as a preference, not as a one-to-one replacement. It should steer the wording when the stated semantic context is present.
- Use external source passages only for quoted or allusive material. Do not replace Stephanos' own wording with the external source translation.
- Do not mention which guidance rules fired in the translation output. The review interface should surface that separately.

F) Philological, grammatical, and orthographic discussion
- When the entry discusses spelling, letters, diphthongs, accents, stress, case, gender, number, dialect, or morphology, preserve the technical claim precisely.
- Preserve Greek letters or digraphs in Greek script when the letter or digraph itself is under discussion, for example ι, ει, οι, υ.
- Prefer transliteration for cited word-forms unless the point depends on Greek spelling, accentuation, a specific letter, or a visible dialectal/prosodic distinction.
- If accentuation or prosody is the topic:
  - τόνος -> stress or accentuation, according to context.
  - ὀξύς describing a word's τόνος -> oxytone, not merely 'acute'.
  - βαρύς describing a word's τόνος -> barytone, not merely 'grave'.
  - Keep the form in a representation that makes the contrast visible. Use Greek script where the Greek spelling or accent is the point.
- When Stephanos cites an inflected form, dialectal form, or poetic form as evidence for another form, do not normalise away the form being demonstrated.
- If the cited form is inflected or dialectal, translate using the English lemma derived from the appropriate Greek nominative where that is needed for consistency. For example, treat Κυταιέος as evidence for Kytaieus from Κυταιεύς, not as a different nominative such as Kytaios.
- Use brief grammatical tags only when they are necessary to make the philological point visible:
  - case: (nom.), (acc.), (gen.), (dat.), (voc.)
  - gender: (m.), (f.), (n.)
  - number: (sing.), (pl.)

G) Comparisons / derivational analogies
- For ὡς + X where X is an analogous form or etymologically related noun, use a form like "(as in 'X')" where this makes the analogy clear.
- For fuller derivational analogies, keep the relation explicit:
  - as 'Byzantios' is from the name Byzantion
  - as in 'Lykaones', from Lykaonia
- Avoid bare 'like X' when the point is morphological analogy.

H) ἀπό, ἀφ' οὗ, and naming/derivation formulae
- If ἀπό + genitive gives an eponym or naming source, prefer 'after X' or 'named after X' rather than a flat 'from X'.
- In entries with temporal naming contrast, ἐκαλεῖτο X ... κέκληται Y -> 'It used to be called X; it is now called/named Y.'
- For ἀφ' οὗ:
  - With a masculine personal antecedent in a naming context, translate 'after whom'.
  - With an explicit neuter antecedent, translate 'from which'.
  - With a dropped neuter antecedent or Stephanos' example-marker usage, translate naturally according to the syntax; use 'as per' only when the Greek construction supports an evidentiary/example sense.
- Avoid archaic 'whence' unless it is clearly the most natural scholarly English.

I) Syntax and restraint
- Translate directly; do not add background explanation, modern bibliography, or parenthetical glosses unless Stephanos gives them.
- Do not add glosses like (synoikia), (kalathos), or explanatory etymologies unless the Greek explicitly defines the term.
- Avoid gratuitous adversatives for δέ.
- Use 'however' only for a real contrast, such as a correction, opposition, exception, or contrastive second item that English needs to mark.
- Avoid 'on the other hand' unless the Greek contrast is strong and English needs it.
- Convert participles into natural English when strict literalness obscures the structure.
- Circumstantial participles may need 'because', 'as', 'when', or a relative clause.
- Preserve uncertainty when the Greek is uncertain, corrupt, or genuinely ambiguous; do not invent a resolution.
- If the source includes bracketed or braced text as part of the lemma main Greek text of the Meineke edition rather than apparatus, translate it and keep brackets if that best reflects the source.
- If the source gives indirect speech under φασί, do not automatically turn it into a formal quotation unless the source punctuation or reference-work style calls for it.

Now translate the provided entry accordingly, and submit it via submit_translation.